Win $20,000. Help build the future of education. Answer the Call for Code. Learn more

Taking selfies (and more) to the next level with open source deep learning models

Using deep learning in an application can produce impressive results, but training a model to be able to make meaningful predictions is a lot of work. While methods like transfer learning help to reduce this workload, the Model Asset eXchange (MAX) provides an even easier solution. By taking advantage of the free-to-use open source models on MAX, developers can find one that meets their needs and start building their application with it in minutes.

In the Deploy a deep learning-powered ‘Magic cropping tool’ code pattern, the MAX Image Segmenter model is used to identify the objects in a user-submitted image on a pixel-by-pixel level. These categorized pixels are then used to generate a version of the image with each unique type of object highlighted in a separate color, called a colormap. Each segment is then split into its own image file that can be downloaded for use elsewhere. As subsequent images are uploaded, they are added to the carousel in the lower portion of the screen and saved in the browser, using PouchDB. From this carousel, images can be reviewed, deleted, or loaded into the “Studio.”

Try it out and let me know what you think!